##// END OF EJS Templates
deltas: set estimated compression upper bound to "3x" instead of "10x"...
deltas: set estimated compression upper bound to "3x" instead of "10x" In pratice, we very rarely observer compression better than "3x" on manifest deltas. Having a more aggressive estimate significantly helps our pathological use case on a private repository. Here are a comparison of timings using different upper bound. Estimated compression | ø | ×10 | ×5 | ×3 | timing | 14.11 | 2.61 | 1.96 | 1.53 | We also tested the impact of this series on an array of public repositories. This shown no impact in either size nor timing. Full data set below for those interested. Size ---- Regarding size, not significant impact have been noticed on neither public nor private repositories. Here are the number we gathered on public repositories: zlib/upperbound | no | 10x | 5x | 3x mercurial | 5 875 730 | 5 875 730 | 5 875 730 | 5 875 730 pypy | 27 782 913 | 27 782 913 | 27 782 913 | 27 782 913 netbeans | 159 161 207 | 159 161 207 | 159 161 207 | 159 959 879 (+0.5%) mozilla-central | 323 841 642 | 323 841 642 | 323 841 642 | 319 867 519 (-2.5%) mozilla-try | 746 649 123 | 746 649 123 | 746 649 123 | 741 155 568 (-0.7%) private-repo | 1 485 287 294 | 1 485 287 294 | 1 485 287 294 | 1 409 248 382 (-5.1%) zstd/upperbound | no | 10x | 5x | 3x mercurial | 5 895 206 | 5 895 206 | 5 895 206 | 5 895 206 pypy | 28 689 230 | 28 689 230 | 28 689 230 | 28 689 230 netbeans | 157 636 387 | 157 636 387 | 157 636 387 | 159 692 678 (+1.3%) mozilla-central | 317 650 281 | 317 650 281 | 317 650 281 | 319 613 603 (+0.6%) mozilla-try | 737 555 275 | 737 555 275 | 737 555 275 | 738 079 473 (+0.1%) private-repo | 1 352 362 982 | 1 352 362 982 | 1 346 961 880 | 1 361 327 384 (+0.7%) Speed ------ Timing gathered using `hg perfrevlogwrite -m`. Value are in seconds. mercurial zlib | no | 10x | 5x | 3x | total | 65.551783 | 65.388887 | 65.260658 | 65.321199 | max | 0.034544 | 0.034571 | 0.034659 | 0.034521 | 99.99% | 0.034544 | 0.034571 | 0.034659 | 0.034521 | zstd | no | 10x | 5x | 3x | total | 49.118449 | 49.054062 | 48.753588 | 48.740230 | max | 0.009338 | 0.009239 | 0.009202 | 0.009178 | 99.99% | 0.007618 | 0.007639 | 0.007626 | 0.007621 | pypy zlib | no | 10x | 5x | 3x | total | 560.865984 | 558.983817 | 559.083815 | 559.349152 | max | 0.219614 | 0.215922 | 0.218112 | 0.218107 | 99.99% | 0.219614 | 0.215922 | 0.218112 | 0.218107 | zstd | no | 10x | 5x | 3x | total | 349.393280 | 347.395819 | 347.185407 | 345.643985 | max | 0.084143 | 0.083536 | 0.081834 | 0.082178 | 99.99% | 0.039445 | 0.039639 | 0.039612 | 0.039175 | netbeans zlib | no | 10x | 5x | 3x | total | 33103.327727 | 33314.932260 | 33211.745233 | 33345.891778 | max | 2.666852 | 2.672059 | 2.662453 | 2.662936 | 99.99% | 2.058772 | 2.070429 | 2.069569 | 2.064653 | zstd | no | 10x | 5x | 3x | total | 20112.102708 | 20095.879719 | 20083.390300 | 20123.221859 | max | 2.063482 | 2.062851 | 2.065229 | 2.060147 | 99.99% | 1.146647 | 1.143794 | 1.142933 | 1.146529 | mozilla zlib | no | 10x | 5x | 3x | total | 41374.102138 | 41418.816773 | 41381.956370 | 41334.280732 | max | 3.383474 | 3.387400 | 3.405711 | 3.387316 | 99.99% | 1.006755 | 1.005954 | 1.007700 | 1.007373 | zstd | no | 10x | 5x | 3x | total | 24689.691520 | 24643.939662 | 24664.630027 | 24664.512714 | max | 1.460822 | 1.449640 | 1.439747 | 1.465304 | 99.99% | 0.527111 | 0.527377 | 0.527807 | 0.527226 |

File last commit:

r38505:4c068365 @58 default
r42669:4a3abb33 default
Show More
namespaces.py
214 lines | 8.0 KiB | text/x-python | PythonLexer
from __future__ import absolute_import
from .i18n import _
from . import (
registrar,
templatekw,
util,
)
def tolist(val):
"""
a convenience method to return an empty list instead of None
"""
if val is None:
return []
else:
return [val]
class namespaces(object):
"""provides an interface to register and operate on multiple namespaces. See
the namespace class below for details on the namespace object.
"""
_names_version = 0
def __init__(self):
self._names = util.sortdict()
columns = templatekw.getlogcolumns()
# we need current mercurial named objects (bookmarks, tags, and
# branches) to be initialized somewhere, so that place is here
bmknames = lambda repo: repo._bookmarks.keys()
bmknamemap = lambda repo, name: tolist(repo._bookmarks.get(name))
bmknodemap = lambda repo, node: repo.nodebookmarks(node)
n = namespace("bookmarks", templatename="bookmark",
logfmt=columns['bookmark'],
listnames=bmknames,
namemap=bmknamemap, nodemap=bmknodemap,
builtin=True)
self.addnamespace(n)
tagnames = lambda repo: [t for t, n in repo.tagslist()]
tagnamemap = lambda repo, name: tolist(repo._tagscache.tags.get(name))
tagnodemap = lambda repo, node: repo.nodetags(node)
n = namespace("tags", templatename="tag",
logfmt=columns['tag'],
listnames=tagnames,
namemap=tagnamemap, nodemap=tagnodemap,
deprecated={'tip'},
builtin=True)
self.addnamespace(n)
bnames = lambda repo: repo.branchmap().keys()
bnamemap = lambda repo, name: tolist(repo.branchtip(name, True))
bnodemap = lambda repo, node: [repo[node].branch()]
n = namespace("branches", templatename="branch",
logfmt=columns['branch'],
listnames=bnames,
namemap=bnamemap, nodemap=bnodemap,
builtin=True)
self.addnamespace(n)
def __getitem__(self, namespace):
"""returns the namespace object"""
return self._names[namespace]
def __iter__(self):
return self._names.__iter__()
def items(self):
return self._names.iteritems()
iteritems = items
def addnamespace(self, namespace, order=None):
"""register a namespace
namespace: the name to be registered (in plural form)
order: optional argument to specify the order of namespaces
(e.g. 'branches' should be listed before 'bookmarks')
"""
if order is not None:
self._names.insert(order, namespace.name, namespace)
else:
self._names[namespace.name] = namespace
# we only generate a template keyword if one does not already exist
if namespace.name not in templatekw.keywords:
templatekeyword = registrar.templatekeyword(templatekw.keywords)
@templatekeyword(namespace.name, requires={'repo', 'ctx'})
def generatekw(context, mapping):
return templatekw.shownames(context, mapping, namespace.name)
def singlenode(self, repo, name):
"""
Return the 'best' node for the given name. What's best is defined
by the namespace's singlenode() function. The first match returned by
a namespace in the defined precedence order is used.
Raises a KeyError if there is no such node.
"""
for ns, v in self._names.iteritems():
n = v.singlenode(repo, name)
if n:
return n
raise KeyError(_('no such name: %s') % name)
class namespace(object):
"""provides an interface to a namespace
Namespaces are basically generic many-to-many mapping between some
(namespaced) names and nodes. The goal here is to control the pollution of
jamming things into tags or bookmarks (in extension-land) and to simplify
internal bits of mercurial: log output, tab completion, etc.
More precisely, we define a mapping of names to nodes, and a mapping from
nodes to names. Each mapping returns a list.
Furthermore, each name mapping will be passed a name to lookup which might
not be in its domain. In this case, each method should return an empty list
and not raise an error.
This namespace object will define the properties we need:
'name': the namespace (plural form)
'templatename': name to use for templating (usually the singular form
of the plural namespace name)
'listnames': list of all names in the namespace (usually the keys of a
dictionary)
'namemap': function that takes a name and returns a list of nodes
'nodemap': function that takes a node and returns a list of names
'deprecated': set of names to be masked for ordinary use
'builtin': bool indicating if this namespace is supported by core
Mercurial.
"""
def __init__(self, name, templatename=None, logname=None, colorname=None,
logfmt=None, listnames=None, namemap=None, nodemap=None,
deprecated=None, builtin=False, singlenode=None):
"""create a namespace
name: the namespace to be registered (in plural form)
templatename: the name to use for templating
logname: the name to use for log output; if not specified templatename
is used
colorname: the name to use for colored log output; if not specified
logname is used
logfmt: the format to use for (i18n-ed) log output; if not specified
it is composed from logname
listnames: function to list all names
namemap: function that inputs a name, output node(s)
nodemap: function that inputs a node, output name(s)
deprecated: set of names to be masked for ordinary use
builtin: whether namespace is implemented by core Mercurial
singlenode: function that inputs a name, output best node (or None)
"""
self.name = name
self.templatename = templatename
self.logname = logname
self.colorname = colorname
self.logfmt = logfmt
self.listnames = listnames
self.namemap = namemap
self.nodemap = nodemap
if singlenode:
self.singlenode = singlenode
# if logname is not specified, use the template name as backup
if self.logname is None:
self.logname = self.templatename
# if colorname is not specified, just use the logname as a backup
if self.colorname is None:
self.colorname = self.logname
# if logfmt is not specified, compose it from logname as backup
if self.logfmt is None:
# i18n: column positioning for "hg log"
self.logfmt = ("%s:" % self.logname).ljust(13) + "%s\n"
if deprecated is None:
self.deprecated = set()
else:
self.deprecated = deprecated
self.builtin = builtin
def names(self, repo, node):
"""method that returns a (sorted) list of names in a namespace that
match a given node"""
return sorted(self.nodemap(repo, node))
def nodes(self, repo, name):
"""method that returns a list of nodes in a namespace that
match a given name.
"""
return sorted(self.namemap(repo, name))
def singlenode(self, repo, name):
"""returns the best node for the given name
By default, the best node is the node from nodes() with the highest
revision number. It can be overriden by the namespace."""
n = self.namemap(repo, name)
if n:
# return max revision number
if len(n) > 1:
cl = repo.changelog
maxrev = max(cl.rev(node) for node in n)
return cl.node(maxrev)
return n[0]
return None